Quantifying Teaching Behaviour in Robot Learning from Demonstration
Learning from demonstration allows for rapid deployment of robot manipulators to a great many tasks, by relying on a person showing the robot what to do rather than programming it. While this approach provides many opportunities, measuring, evaluating and improving the person's teaching ability has remained largely unexplored in robot manipulation research. To this end, a model for learning from demonstration is presented here which incorporates the teacher's understanding of, and influence on, the learner. The proposed model is used to clarify the teacher's objectives during learning from demonstration, providing new views on how teaching failures and efficiency can be defined. The benefit of this approach is shown in two experiments (N=30 and N=36, respectively), which highlight the difficulty teachers have in providing effective demonstrations, and show how ~169-180% improvement in teaching efficiency can be achieved through evaluation and feedback shaped by the proposed framework, relative to unguided teaching.
Code (0)
등록된 구현이 없습니다.
Tasks
Robot ManipulationSimilar Papers 제목 키워드 기반
SKID RAW: Skill Discovery from Raw Trajectories
Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural w…
Variational InferenceInstructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
Learning for Demonstration (LfD) enables robots to acquire new skills by imitating expert demonstrations, allowing users to communicate their instructions in an intuitive manner. Recent progress in LfD often relies on ki…
Teaching Inverse Reinforcement Learners via Features and Demonstrations
Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of lear…
Reinforcement LearningWorking Backwards: Learning to Place by Picking
We present placing via picking (PvP), a method to autonomously collect real-world demonstrations for a family of placing tasks in which objects must be manipulated to specific, contact-constrained locations. With PvP, we…
Behavioural cloningTraining Humans to Train Robots Dynamic Motor Skills
Learning from demonstration (LfD) is commonly considered to be a natural and intuitive way to allow novice users to teach motor skills to robots. However, it is important to acknowledge that the effectiveness of LfD is h…
Open-Ended Question Answering